© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69381
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ెట
    -0.08
     entonces
    -0.08
     약
    -0.08
    Dann
    -0.08
     Howard
    -0.07
    惯
    -0.07
    -0.07
    ternet
    -0.07
    Howard
    -0.07
     ETC
    -0.07
    POSITIVE LOGITS
     сб
    0.08
     caffeine
    0.08
     hogy
    0.07
     tỉnh
    0.07
     sofort
    0.07
    elos
    0.07
     продук
    0.07
     postpone
    0.07
    çe
    0.07
     обратить
    0.07
    Activations Density 0.006%
    No Known Activations